Lesson 10 of 41 · All lessons
Salesforce Agentforce Specialist
0 of 41 complete
1Exam Overview
  1. 1.1Agentforce Specialist Complete Exam Overview
2Prompt Engineering20%
  1. 2.1When to Use Prompt Builder
  2. 2.2Prompt Template Access Controls
  3. 2.3Field Generation and Flex Prompt Template Types
  4. 2.4Grounding Techniques for Prompt Templates
  5. 2.5Creating, Activating, and Executing Prompt Templates
  6. 2.6Best Practices for Writing Effective Prompts
  7. 2.7Trust Layer Security and Privacy Features
  8. 2.8Managing and Preventing Specific Models from Being Accessed
3Data 360 Fundamentals20%
  1. 3.1Agentforce Data Library
  2. 3.2Data 360 Concepts for Agentforce
  3. 3.3Chunking
  4. 3.4Indexing
  5. 3.5Retrievers
  6. 3.6Choosing a Grounding Approach for a Scenario
4AI Agents35%
  1. 4.1How an Agentforce Agent Works
  2. 4.2Agent Building Blocks and Agent Script
  3. 4.3Hybrid Reasoning and Deterministic Behavior
  4. 4.4Agentforce Builder: Canvas and Script Views
  5. 4.5Filters, Variables, and Template Expressions
  6. 4.6Standard and Custom Topics
  7. 4.7Standard and Custom Agent Actions
  8. 4.8Configure Topics, Instructions, and Actions for a Use Case
  9. 4.9Connecting Agents to Digital Experience, Email, Voice, and Slack
  10. 4.10Agent Security Context and Action Execution
  11. 4.11Choosing Between Employee and Service Agents
  12. 4.12When to Use Agent API
5Testing, Deployment, and Maintenance10%
  1. 5.1Testing Agents with Testing Center
  2. 5.2Understanding Testing Center Evaluations
  3. 5.3Deploying Agents from Sandbox to Production
  4. 5.4Deploying Prompt Templates Between Environments
  5. 5.5Reviewing Agent Behavior After Changes
6Governance and Observability10%
  1. 6.1Managing and Monitoring Agents
  2. 6.2Agent Analytics and Performance Signals
  3. 6.3Identifying Opportunities to Optimize Agent Behavior
  4. 6.4Using Observations to Guide Improvements
7Multi-Agent Orchestration5%
  1. 7.1Choosing a Multi-Agent Architecture
  2. 7.2Orchestrators and Connected Subagents
  3. 7.3Handoff and Supervisor Modes
  4. 7.4Model Context Protocol (MCP)
  5. 7.5Agent-to-Agent (A2A) Communication

Section 3 · Data 360 Fundamentals · 20% of exam

3.1 Agentforce Data Library

4 min read Updated Nov 16, 2026

Exam objective

Explain the purpose of an Agentforce Data Library, its supported source choices, and how a library connects trusted information to Agentforce features.

What a data library does?

An Agentforce Data Library is a managed way to connect an Agentforce feature to selected organizational knowledge. It prepares supported content for search and retrieval, then makes relevant passages available to a prompt or agent at run time. The model can use that retrieved context to answer with information specific to the business instead of relying only on its general training. This process is called grounding. A library supports retrieval-augmented generation (RAG): retrieve useful source content, add it to the prompt, and generate a response using both the user’s request and the retrieved context. Grounding improves relevance, but it does not guarantee that every answer is correct. Source quality, indexing, retrieval, permissions, prompt instructions, and testing still matter.

Choose a source before creating the library

Salesforce Help currently describes Salesforce Knowledge, uploaded files, and custom retrievers as data source choices for a new library. A library uses one source type at a time, and you cannot change that source after creation. A feature can use only one data library at a time. New web-search libraries are not supported; existing ones are read-only. For current public web information, consider the separate Search the Web capability where appropriate. Verify source availability in current Help.

Setup and readiness

Data 360 must be set up before Agentforce Data Libraries can be used, and libraries consume Data 360 credits. When a library is created, Salesforce automates data preparation steps such as creating or mapping data objects and setting up a search index and retriever. The content must finish processing before it is ready for use. In Agentforce Builder, select the library and confirm its status is Ready. Then ensure the agent has the Answer Questions with Knowledge action if that is the intended integration. The action can provide structured answers and, when Show Sources is enabled, include source information. Test after indexing completes; a saved library that is still processing should not be treated as a usable source.

Plan for ownership and access

A library is not a substitute for deciding which content belongs in an answer. Select only authoritative, current material. For Knowledge, choose the fields that contain useful, well-formed information; for uploaded files, confirm the documents are readable and appropriate for the audience. Consider how updates to source records reach the index and who owns checking freshness. Also consider Data 360 setup, permissions, licensing, credit use, and the relevant agent’s security context. A source that is technically searchable may still be inappropriate for a particular user or use case. Check Salesforce permissions and data governance independently of retrieval configuration. Scenario: support policy answers

Suppose a service agent must answer questions from a maintained set of approved return policies. If the policies are published as Knowledge articles, a Knowledge-based library is a direct fit. The organization selects relevant fields, waits for the library to become Ready, connects it to the agent, and tests questions about both common and edge cases. If the same material exists only as approved documents, an uploaded-file library may fit better. If the required information is held in a Data 360 search index or another supported setup, a custom retriever may be appropriate. The correct choice depends on where the authoritative content lives and how it must be searched, not on which option sounds most advanced.

When a scenario asks how to ground an agent in approved business content, identify the authoritative source first, then choose the matching library type and verify that it is Ready.

New web-search libraries are not available. Existing web-search libraries are read-only; use the current Search the Web feature for new web retrieval use cases where appropriate.

Extra concept: A library automates RAG setup, but source maintenance, access checks, and evaluation remain essential.

Official references:

  • Agentforce Data Library https://help.salesforce.com/s/articleView?id=ai.data_library_parent.htm&language=en_US&type=5
  • Choose a Data Source for Your Library https://help.salesforce.com/s/articleView?id=ai.data_library_choose_data_source.htm&language=en_US&type=5
  • Use the Answer Questions with Knowledge Action https://help.salesforce.com/s/articleView?id=ai.agent_setup_data_sources.htm&language=en_US&type=5

Key takeaways

  • A data library connects supported trusted data to Agentforce through grounding and retrieval.
  • A library uses one source type; select it carefully because it cannot be changed later.
  • Confirm Data 360 setup, credits, Ready status, the right agent action, and source access before testing.

Check your knowledge

Answer exam-style Data 360 Fundamentals questions with answers and explanations.

Practice Data 360 Fundamentals
Finished this lesson? Mark it complete to track your progress.

Ready for the real exam?

Take the timed Salesforce Agentforce Specialist simulator: same number of questions, same time limit.

Get Complete Access